┌─────────┐   ┌─────────┐   ┌─────────┐   ┌─────────┐
│ Hermes  │   │  Trae   │   │ Cursor  │   │ Claude  │
└────┬────┘   └────┬────┘   └────┬────┘   └────┬────┘
     │ MCP         │ MCP         │ MCP         │ MCP
     ▼             ▼             ▼             ▼
┌──────────────────────────────────────────────────┐
│           MemoryBuddy Worker (Cloudflare)         │
│                                                  │
│   /mcp  → MCP Server (5 tools, Streamable HTTP)  │
│   /chat → HTTP API (SSE streaming + auto-extract)│
│   /memory/:userId → REST API                     │
└──────────┬──────────────────┬────────────────────┘
           │                  │
     ┌─────▼─────┐    ┌──────▼──────┐
     │ D1 (facts)│    │ Vectorize   │
     │ SQLite DB │    │ (embeddings)│
     └───────────┘    └─────────────┘

git clone https://github.com/Trainspotting31/memory-buddy.git
cd memory-buddy
npm install

npx wrangler login

# Create D1 database
npx wrangler d1 create memory-buddy-db

# Create Vectorize index
npx wrangler vectorize create memory-buddy-index --dimensions 768 --metric cosine

# Initialize database schema
npx wrangler d1 execute memory-buddy-db --remote --file=schema.sql

npx wrangler deploy

hermes mcp add memory-buddy --url https://memory-buddy.<your-subdomain>.workers.dev/mcp

{
  "mcpServers": {
    "memory-buddy": {
      "type": "streamable-http",
      "url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "memory-buddy": {
      "url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "memory-buddy": {
      "type": "streamable-http",
      "url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
    }
  }
}

Endpoint: https://memory-buddy.<your-subdomain>.workers.dev/mcp
Transport: Streamable HTTP
Auth: None (or add your own)

curl -N -X POST https://your-worker.workers.dev/chat \
  -H "Content-Type: application/json" \
  -d '{"userId":"user123","message":"Hi! I'm John and I love espresso."}'

curl https://your-worker.workers.dev/memory/user123

curl -X DELETE https://your-worker.workers.dev/memory/user123

curl https://your-worker.workers.dev/health

[vars]
LLM_MODEL = "@cf/meta/llama-3.2-3b-instruct"  # Default: Workers AI (free)

# Optional: use external LLM instead of Workers AI
LLM_API_KEY = "sk-your-key"
LLM_API_BASE = "https://api.openai.com/v1"
LLM_MODEL = "gpt-4o-mini"

memory-buddy/
├── src/
│   ├── index.ts          # Hono router: /mcp + /chat + /memory + /health
│   ├── mcp.ts            # MCP Server factory (5 tools, stateless)
│   ├── agent-do.ts       # Durable Object: chat session + memory orchestration
│   ├── llm.ts            # LLM abstraction (Workers AI / OpenAI-compatible)
│   └── memory/
│       ├── extract.ts    # LLM-powered fact extraction
│       ├── retrieve.ts   # Hybrid retrieval (D1 + Vectorize)
│       └── summarize.ts  # Conversation summarization
├── public/index.html     # Built-in demo chat UI
├── schema.sql            # D1 database schema
├── wrangler.toml.example # Cloudflare config template
└── package.json